SKILLEMALL.ai
GitHub ↗ RU Sign in

BC nemotron-3-5-super-vl-finance-lora

Run the Nemotron-3.5 Super VL finance LoRA cookbook (NeMo Megatron-Bridge) end-to-end for the user, on one 8-GPU node or a Slurm cluster: data prep, checkpoint conversion, text+vision LoRA fine-tuning of the 120B-A12B model, merge to a Hugging Face checkpoint, and a vLLM try-out. Use when the user wants to run this cookbook, fine-tune Nemotron-3.5 Super VL with LoRA, or adapt it to their hardware.

NVIDIA-NeMo/Nemotron Agent Skills author: NVIDIA-NeMo 15 files · 12 scripts body ≈ 1 433 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Run the Nemotron-3.5 Super VL finance LoRA cookbook (NeMo Megatron-Bridge) end-to-end for the user, on one 8-GPU node or a Slurm cluster: data prep…

As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency

ProcedureAI and agentstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
91/100
safety, quality, tests
Safety 60%
98
Quality 40%
80
Run on models
none yet
Process rating
C
54/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Consistency w 8
40
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 2

    ✓ No critical or high findings

    Medium and low: 2
    • low Secrets in code secret-high-entropy-token train.py:42
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      "Nemo…sor",
      quoted
    • low Secrets in code secret-high-entropy-token train.py:43
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      registry._MODEL_COLLATE_SPECS["Nemo…sor"],
      quoted

    Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note edit-residue the text marks something as outdated (lines 84): check that old rules are not kept next to new ones — the full check reads the text for contradictions

    Process rating: all ten parameters 54/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 40Consistency. Frontmatter name (nemotron-3-5-super-vl-finance-lora) differs from the folder (nemo-megatron-bridge)
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 24 steps
    • 100Execution cost. Instruction body is 1433 tokens
    • 100Running it twice. Mutating operations check current state
    • 100Progress reporting. Reports progress
    • low The response is described with custom markup (4 tags): a typed call is more reliable

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +3Description length 400: enough signal without eating the budget
    • +4Structure: 7 headings
    • +3Step-by-step instructions: 24 items

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.